A Unified Bayesian Framework for Adaptive Visual Tracking

Video target tracking is a critical problem in the field of computer vision. Particle filters have been proven to be very useful in target tracking for nonlinear and non-Gaussian estimation problems. Although most existing algorithms are able to track targets well in controlled environments, it is often difficult to achieve automated and robust tracking of pedestrians in video sequences if there are various changes in target appearance or surrounding illumination. To surmount these difficulties, this paper presents multitarget tracking of pedestrians in video sequences based on particle filters. In order to improve the efficiency and accuracy of the detection, the algorithm firstly obtains target regions in training frames by combining the methods of background subtraction and Histogram of Oriented Gradient (HOG) and then establishes discriminative appearance model by generating patches and constructing codebooks using superpixel and Local Binary Pattern (LBP) features in those target regions. During the process of tracking, the algorithm uses the similarity between candidates and codebooks as observation likelihood function and processes severe occlusion condition to prevent drift and loss phenomenon caused by target occlusion. Experimental results demonstrate that our algorithm improves the tracking performance in complicated real scenarios.

In recent years, online building an adaptive target appearance model has been investigated for robust visual tracking in a dynamic environment. However one inherent problem of adaptive appearance trackers is drift, a gradual adaptation of the tracker to non-targets. To alleviate this problem, we consider visual tracking in a novel online manifold regularization (Online-MR) setting where labeled and unlabeled data arrive sequentially in large volume for tracker update. A discriminative target appearance model based on Haar wavelet is learned at each frame and its output score is used as the input sample feature for Online-MR tracker learning. Such a combination of Online-MR semi-supervised learning and online appearance model adaptation results in a robust tracking scheme that can prevent the tracker from drifting while retain its adaptation to appearance changing. Experimental results demonstrate the effectiveness of the proposed method from comparisons with adaptive appearance model based trackers on several challenging video sequences.

Visual tracking has been widely used in robot systems, and numerous approaches for visual tracking have been proposed. However, developing a robust and real-time visual tracking algorithm which can adaptively track the varying appearance of target under challenging conditions for mobile robot is still an open problem. This paper presents an adaptive probabilistic tracking algorithm with multiple cues integration. An effective evaluation function is proposed to evaluate each cue used for tracking based on their discriminating abilities between foreground and background. Then the likelihood functions of the cues are integrated in particle filter framework with different weights determined based on the evaluation scores. A novel target model updating strategy is proposed to adapt to the varying appearance of target resisting gradual drift which is still an unsolved problem in many adaptive tracking algorithms. Experimental results on a mobile robot demonstrate the robust performance of the proposed algorithm under challenging conditions.

Appearance change of moving targets is a challenging problem in visual tracking. In this paper, we present a novel visual object tracking algorithm based on the observation dependent hidden Markov model (OD-HMM) framework. The observation dependency is computed by structure complexity coefficients (SCC) which is defined to predict the target appearance change. Unlike conventional methods addressing the appearance change problem by investigating different online appearance models, we handle this problem by addressing the fundamental reason of motion -related appearance change during visual tracking. Based on the analysis of motion-related appearance change, we investigate the relationship between the structure of the object surface and the appearance stability. The appearance of complex structural regions is easier to change compared with that of smooth structural regions with object moving. Based on this, we define SCC to predict the appearance stability of moving objects. Different from the standard HMM-based tracking algorithms where observations between different frames are assumed to be independent, we consider the observation dependency between consecutive frames with the information provided by SCC. Moreover , we present a novel outlier removing method in appearance model updating which helps to avoid error accumulation. Experimental results on challenging video sequences demonstrate that the proposed visual tracking algorithm with OD-HMM and SCC achieves better performance than existing related tracking algorithms.

Current state-of-the-art trackers rely only on a target appearance model in order to localize the object in each frame. Such approaches are however prone to fail in case of e.g. fast appearance changes or presence of distractor objects, where a target appearance model alone is insufficient for robust tracking. Having the knowledge about the presence and locations of other objects in the surrounding scene can be highly beneficial in such cases. This scene information can be propagated through the sequence and used to, for instance, explicitly avoid distractor objects and eliminate target candidate regions. In this work, we propose a novel tracking architecture which can utilize scene information for tracking. Our tracker represents such information as dense localized state vectors, which can encode, for example, if a local region is target, background, or distractor. These state vectors are propagated through the sequence and combined with the appearance model output to localize the target. Our network is learned to effectively utilize the scene information by directly maximizing tracking performance on video segments. The proposed approach sets a new state-of-the-art on 3 tracking benchmarks, achieving an AO score of $$63.6\%$$ on the recent GOT-10k dataset.

Video object segmentation (VOS) is a highly challenging problem since the initial mask, defining the target object, is only given at test-time. The main difficulty is to effectively handle appearance changes and similar background objects, while maintaining accurate segmentation. Most previous approaches fine-tune segmentation networks on the first frame, resulting in impractical frame-rates and risk of overfitting. More recent methods integrate generative target appearance models, but either achieve limited robustness or require large amounts of training data. We propose a novel VOS architecture consisting of two network components. The target appearance model consists of a light-weight module, which is learned during the inference stage using fast optimization techniques to predict a coarse but robust target segmentation. The segmentation model is exclusively trained offline, designed to process the coarse scores into high quality segmentation masks. Our method is fast, easily trainable and remains highly effective in cases of limited training data. We perform extensive experiments on the challenging YouTube-VOS and DAVIS datasets. Our network achieves favorable performance, while operating at higher frame-rates compared to state-of-the-art. Code and trained models are available at https://github.com/andr345/frtm-vos.

One of the main difficulties in visual tracking is to take into account appearance changes (not only of the target but also of or due to the scene, illumination for example). The use of a Bayesian framework is very flexible and has proven to be very efficient in visual tracking. Moreover, color or greylevel histograms allow to track an objet with a low computational cost. The recently proposed color-based trackers integrated in a probabilistic framework are efficient for a given application (face tracking for example) but can not be generalized easily, due to the initialization and the adjustment of the different tracker parameters that are dependent on the input sequence. This paper presents a method based on color integrated in a particle filter that allows to cope with some of the usual problems of visual tracking (occlusions, target appearance changes, changes in resolution or in illumination) and to adapt easily to different applications (tracking of structures in aerial imagery as well as football players). The novelty of the tracker is its ability to automatically regulate all the parameters needed for tracking, which makes it flexible and easily usable for different applications.

In visual tracking, developing an efficient appearance model is a challenging task due to the influence of various factors, such as illumination variation, occlusion, background clutter, and so on. Existing tracking algorithms use appearance samples from previous frames to form a template set upon which target appearance models are built. However, these appearance models are data-dependent, so they may be corrupted by significant appearance variation. It is difficult to update the templates in challenging environments. In this paper, we propose a robust visual tracking algorithm with an adaptive appearance model using a point-to-set metric learning technique. To do this, we first model a target representation using a set of target templates and a regularized affine hull (RAH) spanned by the target templates. Then, we learn a point-to-set distance metric, which is incorporated into the optimization process to obtain an adaptive target representation. The RAH model covers unseen target appearances by affine combinations of the target templates. Based on the proposed target appearance model, we design an effective template update scheme by adjusting the weights of the target templates. Experimental results on challenging video sequences with comparisons to several state-of-the-art tracking algorithms demonstrate the effectiveness and robustness of the proposed tracking algorithm.

Significant progress is made in the field of object tracking recently. Especially, trackers based on deep learning and correlation filters both have achieved excellent performance. However, object tracking still faces some challenging problems such as deformation and illumination. In such kinds of situations, the accuracy and precision of tracking algorithms plunge as a result. It is imminent to find a solution to this situation. In this paper, we propose a tracking algorithm based on features extracted by residual network called Resnet features and cascaded correlation filters to improve precision and accuracy. Firstly, features extracted by a deep residual network trained on other image processing datasets, are robust enough and retain higher resolution, therefore, we exploit Resnet-101 pretrained offline to obtain features extracted by middle and high layers for target appearance model representation. Resnet-101 is deeper compared with other deep neural networks which means it contains more semantic information. Then, the method we propose to combine our correlation filters is superior. We propose cascaded correlation filters generated by handcraft, middle-level and high-level features from residual network to gain better competence. Handcraft features localize target precisely because they contain more spatial details while Resnet features are robust to the target appearance change because they retain more semantic information. Finally, we conduct extensive experiments on OTB2013 and OTB2015 benchmark. The experimental results show that our tracker achieves high performance under all kinds of challenges and performs favorably against other state-of-the-art trackers.

Deep learning has been widely used in many visual recognition tasks owing to its powerful representation ability. However, online learning is a bottleneck to obstruct the application of deep learning in visual tracking. Although many algorithms have discarded the process of online learning during tracking, they demonstrate poor robustness to the online adaptation to appearance changes of the target. In this study, the authors design a tree structure specifically for online learning, which enables the appearance model to be updated smoothly. Once the target appearance has changed severely, a new branch is generated to avoid the fuzzy boundary of classification. In addition, active learning technique and artificial data are employed in the update to make the best of the limited knowledge about the interesting object during the tracking process. The proposed algorithm is evaluated on OTB2013 and VOT2017 benchmark and outperforms many state-of-the-art methods.

Visual tracking is an important area in computer vision. How to deal with illumination and occlusion problems is a challenging issue. This paper presents a novel and efficient tracking algorithm to handle such problems. On one hand, a target’s initial appearance always has clear contour, which is light-invariant and robust to illumination change. On the other hand, features play an important role in tracking, among which convolutional features have shown favorable performance. Therefore, we adopt convolved contour features to represent the target appearance. Generally speaking, first-order derivative edge gradient operators are efficient in detecting contours by convolving them with images. Especially, the Prewitt operator is more sensitive to horizontal and vertical edges, while the Sobel operator is more sensitive to diagonal edges. Inherently, Prewitt and Sobel are complementary with each other. Technically speaking, this paper designs two groups of Prewitt and Sobel edge detectors to extract a set of complete convolutional features, which include horizontal, vertical and diagonal edges features. In the first frame, contour features are extracted from the target to construct the initial appearance model. After the analysis of experimental image with these contour features, it can be found that the bright parts often provide more useful information to describe target characteristics. Therefore, we propose a method to compare the similarity between candidate sample and our trained model only using bright pixels, which makes our tracker able to deal with partial occlusion problem. After getting the new target, in order to adapt appearance change, we propose a corresponding online strategy to incrementally update our model. Experiments show that convolutional features extracted by well-integrated Prewitt and Sobel edge detectors can be efficient enough to learn robust appearance model. Numerous experimental results on nine challenging sequences show that our proposed approach is very effective and robust in comparison with the state-of-the-art trackers.

Model-free tracking is a widely-accepted approach to track an arbitrary object in a video using a single frame annotation with no further prior knowledge about the object of interest. Extending this problem to track multiple objects is really challenging because: a) the tracker is not aware of the objects' type while trying to distinguish them from background (detection task), and b) The tracker needs to distinguish one object from other potentially similar objects (data association task) to generate stable trajectories. In order to track multiple arbitrary objects, most existing model-free tracking approaches rely on tracking each target individually by updating their appearance model independently. Therefore, in this scenario they often fail to perform well due to confusion between the appearance of similar objects, their sudden appearance changes and occlusion. To tackle this problem, we propose to use both appearance and motion models, and to learn them jointly using graphical models and deep neural networks features. We introduce an indicator variable to predict sudden appearance change and/or occlusion. When these happen, our model does not update the appearance model thus avoiding using the background and/or incorrect object to update the appearance of the object of interest mistakenly, and relies on our motion model to track. Moreover, we consider the correlation among all targets, and seek the joint optimal locations for all targets simultaneously as a graphical model inference problem. We learn the joint parameters for both appearance model and motion model in an online fashion under the framework of LaRank. Experiment results show that our method achieved superior performance compared to the competitive methods.

This paper addresses the challenging issue of target tracking and appearance learning in Forward Looking Infrared (FLIR) sequences. Tracking and appearance learning are formulated as a joint state estimation problem with two parallel inference processes. Specifically, a new adaptive Kalman filter is proposed to learn histogram-based target appearances. A particle filter is used to estimate the target position and size, where the learned appearance plays an important role. Our appearance learning algorithm is compared against two existing methods and experiments on the AMCOM FLIR dataset validate its effectiveness.

Robust infrared target tracking based on particle filter with embedded saliency detection

Visual tracking is challenging due to appearance changes caused by motion, illumination, occlusion and pose, among others. For these local changes, appearance model based tracking algorithms, such as MILtracker [8], have adopted local features and most recently extended to compressive domain, namely Compressive Tracking [13], for the real-time performance. However, the motion information is missed out from these trackers and assumptions on target motion have been made by predefined search radii. In this paper, the motion information has been integrated into appearance model based tracking by introducing motion estimator, i.e., particle filters. The experiments show that motion estimator could improve the performance of appearance based trackers especially when the target is with motion variety.